| Type | Ongoing free tier · renewing-quota | Ongoing free tier · renewing-quota |
|---|
| What's free | 10,000 Neurons/day, all account plans | A rotating set of models with a :free suffix (16 on 2026-10-08; count fluctuates), single API across many providers |
|---|
| Rate limits | 10,000 Neurons/day (free allocation). Per-task request limits: text generation 300 requests/min (models that require Workers Paid: 20 requests/min per model); text embeddings 3,000/min; speech recognition, text-to-image, translation, image-to-text 720/min | 20 req/min; 50 req/day under 10 credits purchased lifetime, 1000 req/day once 10+ credits purchased (one-time, not a subscription) |
|---|
| Expires | no expiry | no expiry |
|---|
| The catch | Resets daily at 00:00 UTC; overage on a Workers Paid plan bills at $0.011/1,000 Neurons. A few models (e.g. Kimi K2.6/K2.7-code, GLM-5.2) now require a Workers Paid plan | ToS (Jul 2026) prohibits reselling API access or building a competing service — platform-wide, not just the free models; per-model terms still apply |
|---|
| Credit card | not required | not required |
|---|
| Phone verification | not required | not required |
|---|
| Commercial use | allowed | allowed |
|---|
| OpenAI-compatible | yes https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1
| yes https://openrouter.ai/api/v1
|
|---|
| Modalities | text, embeddings, image, audio | text, vision |
|---|
| Free models (sample) | @cf/meta/llama-3.3-70b-instruct-fp8-fast @cf/meta/llama-3.1-8b-instruct @cf/mistralai/mistral-small-3.1-24b-instruct @cf/qwen/qwen2.5-coder-32b-instruct @cf/deepseek-ai/deepseek-r1-distill-qwen-32b @cf/google/gemma-3-12b-it | cohere/north-mini-code:free google/gemma-4-26b-a4b-it:free google/gemma-4-31b-it:free liquid/lfm-2.5-2.6b:free nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free poolside/laguna-s-2.1:free |
|---|
| Official docs | developers.cloudflare.com/workers-ai/platform/pricing/ | openrouter.ai/docs/api-reference/limits |
|---|
| Last verified | 2026-10-08 | 2026-10-08 |
|---|